Automatic fetal biometry prediction using a novel deep convolutional network architecture |
| |
Affiliation: | 1. BCN MedTech, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain;2. BCNatal | Fetal Medicine Research Center (Hospital Clínic and Hospital Sant Joan de Déu), University of Barcelona, Barcelona, Spain; Institut d''Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain and Centre for Biomedical Research on Rare Diseases (CIBER-ER), Barcelona, Spain;3. ICREA, Barcelona, Spain;2. School of Computer Science, University of Sydney, Sydney, New South Wales, Australia;3. Sydney Medical School, University of Sydney, Sydney, New South Wales, Australia;2. Medical Ultrasound Imaging Center, Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Nijmegen, The Netherlands;3. St. Luke''s Catholic Hospital and College of Nursing and Midwifery, Wolisso, Ethiopia;4. Physics of Fluids Group, MIRA, University of Twente, The Netherlands;5. Fraunhofer MEVIS, Bremen, Germany;1. National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China;2. Medical Ultrasound Image Computing (MUSIC) Laboratory, Shenzhen University, Shenzhen, China;3. Department of Ultrasound, Luohu People’s Hospital, Shenzhen, China |
| |
Abstract: | PurposeFetal biometric measurements face a number of challenges, including the presence of speckle, limited soft-tissue contrast and difficulties in the presence of low amniotic fluid. This work proposes a convolutional neural network for automatic segmentation and measurement of fetal biometric parameters, including biparietal diameter (BPD), head circumference (HC), abdominal circumference (AC), and femur length (FL) from ultrasound images that relies on the attention gates incorporated into the multi-feature pyramid Unet (MFP-Unet) network.MethodsThe proposed approach, referred to as Attention MFP-Unet, learns to extract/detect salient regions automatically to be treated as the object of interest via the attention gates. After determining the type of anatomical structure in the image using a convolutional neural network, Niblack's thresholding technique was applied as pre-processing algorithm for head and abdomen identification, whereas a novel algorithm was used for femur extraction. A publicly-available dataset (HC18 grand-challenge) and clinical data of 1334 subjects were utilized for training and evaluation of the Attention MFP-Unet algorithm.ResultsDice similarity coefficient (DSC), hausdorff distance (HD), percentage of good contours, the conformity coefficient, and average perpendicular distance (APD) were employed for quantitative evaluation of fetal anatomy segmentation. In addition, correlation analysis, good contours, and conformity were employed to evaluate the accuracy of the biometry predictions. Attention MFP-Unet achieved 0.98, 1.14 mm, 100%, 0.95, and 0.2 mm for DSC, HD, good contours, conformity, and APD, respectively.ConclusionsQuantitative evaluation demonstrated the superior performance of the Attention MFP-Unet compared to state-of-the-art approaches commonly employed for automatic measurement of fetal biometric parameters. |
| |
Keywords: | Fetal biometry Ultrasound imaging Deep learning Convolutional neural network Image classification |
本文献已被 ScienceDirect 等数据库收录! |
|